# Learning Bilingual Word Representations by Marginalizing Alignments

arXiv: https://arxiv.org/abs/1405.0947 · HTML: https://mlsanity.com/paper/1405.0947/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 May 2014.

## Built on by (most cited first, 2 of 2)

- [Parallel-SFT: Improving Zero-Shot Cross-Programming-Language Transfer for Code RL](https://mlsanity.com/paper/2604.20835/) (2026)
- [Corpus-Based Approaches to Igbo Diacritic Restoration](https://mlsanity.com/paper/2601.18380/) (2026)

## Abstract (arXiv)

We present a probabilistic model that simultaneously learns alignments and distributed representations for bilingual data. By marginalizing over word alignments the model captures a larger semantic context than prior work relying on hard alignments. The advantage of this approach is demonstrated in a cross-lingual classification task, where we outperform the prior published state of the art.